© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260968
    Prev
    Next
    INDEX
    Explanations

    logical or logical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ۰
    1.51
     to
    1.46
     I
    1.44
    al
    1.23
    ০০
    1.22
    an
    1.06
    s
    1.04
    ।’
    1.01
    LEN
    1.01
    ০
    0.99
    POSITIVE LOGITS
    ल
    1.59
     obten
    1.54
    ل
    1.43
    ל
    1.43
    ت
    1.42
    न
    1.38
    л
    1.36
    वैसे
    1.31
     préférable
    1.27
     inclinations
    1.26
    Activations Density 0.000%

    No Known Activations